© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47862
    Prev
    Next
    INDEX
    Explanations

    many applications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Cá
    -0.88
    鍚
    -0.86
    ÁN
    -0.84
    Ál
    -0.79
    Zag
    -0.76
    ضاء
    -0.76
    whitespace
    -0.76
    lapse
    -0.75
    葫芦
    -0.74
    breviations
    -0.73
    POSITIVE LOGITS
     biological
    1.69
     engineering
    1.54
     applications
    1.51
     physical
    1.40
     sciences
    1.26
     biology
    1.26
     problems
    1.22
     economics
    1.20
     phenomena
    1.19
    Applications
    1.18
    Activations Density 0.197%

    No Known Activations